Model comparison
GLM-5.2 vs Qwen3.5 397B-A17B
GLM-5.2 is the stronger model overall, scoring 51.1 to 46.0 on the Noometry Index. Qwen3.5 397B-A17B costs 1.6× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Alibaba (Qwen)Summary
- They share 31 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Qwen3.5 397B-A17B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.7 to 46.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 59.2% for GLM-5.2 and 31.2% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 accepts more context: 1M tokens versus 262K.
Side by side
| GLM-5.2 | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 51.1 | 46.0 |
| Released | 2026-06-13 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $1.40 | $0.60 |
| Output $ / M tokens | $4.40 | $3.60 |
| Results tracked | 51 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | GLM-5.2 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1603 | 1400 |
| LMArena Coding | 1485 | 1465 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use Too close to call
GLM-5.2: 32.4 (#63), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | GLM-5.2 | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | 45.2% | 24.9% |
| τ²-bench Banking | 37.1% | 9.8% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | GLM-5.2 | Qwen3.5 397B-A17B |
|---|---|---|
| Kagi LLM Benchmark | 62.6% | 73.7% |
| NYT Connections (extended) | 74.3% | 58.9% |
| Chess Puzzles | 21% | 13% |
| LMArena Hard Prompts | 1480 | 1448 |
| Mystery Game Puzzles | 19% | 18% |
| DTBench | 93.6% | 87.5% |
| LMCA | 45.8% | 37.9% |
| Epoch Capabilities Index | 151.78 | 146.65 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| Thematic Generalization | — | 65.1% |
| EBR-Bench | 9.5% | — |
| Surface Evolver Bench | 55.6% | — |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | GLM-5.2 | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 31.2% |
| OTIS Mock AIME 2024-2025 | 86.4% | 88.9% |
| LMArena Math | 1482 | 1454 |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | GLM-5.2 | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 91.9% | 86.4% |
| LMArena Expert | 1486 | 1462 |
| SimpleQA Verified | 34.2% | — |
Multimodal Not comparable
GLM-5.2: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | GLM-5.2 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | GLM-5.2 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1459 | 1430 |
| LMArena Chinese | 1519 | 1500 |
| LMArena French | 1479 | 1461 |
| LMArena German | 1468 | 1447 |
| LMArena Japanese | 1451 | 1426 |
| LMArena Korean | 1445 | 1384 |
| LMArena Russian | 1466 | 1429 |
| LMArena Spanish | 1477 | 1441 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | GLM-5.2 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1465 | 1424 |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | GLM-5.2 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1479 | 1442 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | GLM-5.2 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1470 | 1438 |
| LMArena Creative Writing | 1462 | 1401 |
| EQ-Bench Creative Writing | 1757 | 1478 |
| LMArena Multi-Turn | 1469 | 1446 |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than Qwen3.5 397B-A17B?
GLM-5.2 is the stronger model overall, scoring 51.1 to 46.0 on the Noometry Index. Qwen3.5 397B-A17B costs 1.6× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Which is cheaper, GLM-5.2 or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or Qwen3.5 397B-A17B better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 262K.
How many benchmarks do GLM-5.2 and Qwen3.5 397B-A17B share?
31 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Qwen3.5 397B-A17B has 36.